Neural layer with linear neurons, with an identity activation function. can be used as a hidden layer or an output layer.
Each neuron in the layer is connected to all the neurons in all the layers that connect into this layer.
Activations for each train/test case are computed according to \( b + \sum_i W_i x_i \) where \( b \) is the bias vector, \( W_i \) is the weights matrix between this layer and layer i of its inputs, and \( x_i \) is the activations vector of layer i.
The layout of the parameter vector of this layer is as follows:
When used as an output layer, a squared error measure is used
在文件 NeuralLinearLayer.h 第 63 行定义.
Public 成员函数 | |
CNeuralLinearLayer () | |
CNeuralLinearLayer (int32_t num_neurons) | |
virtual | ~CNeuralLinearLayer () |
virtual void | initialize_neural_layer (CDynamicObjectArray *layers, SGVector< int32_t > input_indices) |
virtual void | initialize_parameters (SGVector< float64_t > parameters, SGVector< bool > parameter_regularizable, float64_t sigma) |
virtual void | compute_activations (SGVector< float64_t > parameters, CDynamicObjectArray *layers) |
virtual void | compute_gradients (SGVector< float64_t > parameters, SGMatrix< float64_t > targets, CDynamicObjectArray *layers, SGVector< float64_t > parameter_gradients) |
virtual float64_t | compute_error (SGMatrix< float64_t > targets) |
virtual void | enforce_max_norm (SGVector< float64_t > parameters, float64_t max_norm) |
virtual float64_t | compute_contraction_term (SGVector< float64_t > parameters) |
virtual void | compute_contraction_term_gradients (SGVector< float64_t > parameters, SGVector< float64_t > gradients) |
virtual void | compute_local_gradients (SGMatrix< float64_t > targets) |
virtual const char * | get_name () const |
virtual void | set_batch_size (int32_t batch_size) |
virtual bool | is_input () |
virtual void | compute_activations (SGMatrix< float64_t > inputs) |
virtual void | dropout_activations () |
virtual int32_t | get_num_neurons () |
virtual int32_t | get_width () |
virtual int32_t | get_height () |
virtual void | set_num_neurons (int32_t num_neurons) |
virtual int32_t | get_num_parameters () |
virtual SGMatrix< float64_t > | get_activations () |
virtual SGMatrix< float64_t > | get_activation_gradients () |
virtual SGMatrix< float64_t > | get_local_gradients () |
virtual SGVector< int32_t > | get_input_indices () |
virtual CSGObject * | shallow_copy () const |
virtual CSGObject * | deep_copy () const |
virtual bool | is_generic (EPrimitiveType *generic) const |
template<class T > | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
void | unset_generic () |
virtual void | print_serializable (const char *prefix="") |
virtual bool | save_serializable (CSerializableFile *file, const char *prefix="") |
virtual bool | load_serializable (CSerializableFile *file, const char *prefix="") |
void | set_global_io (SGIO *io) |
SGIO * | get_global_io () |
void | set_global_parallel (Parallel *parallel) |
Parallel * | get_global_parallel () |
void | set_global_version (Version *version) |
Version * | get_global_version () |
SGStringList< char > | get_modelsel_names () |
void | print_modsel_params () |
char * | get_modsel_param_descr (const char *param_name) |
index_t | get_modsel_param_index (const char *param_name) |
void | build_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict) |
virtual void | update_parameter_hash () |
virtual bool | parameter_hash_changed () |
virtual bool | equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false) |
virtual CSGObject * | clone () |
Protected 成员函数 | |
virtual void | load_serializable_pre () throw (ShogunException) |
virtual void | load_serializable_post () throw (ShogunException) |
virtual void | save_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_post () throw (ShogunException) |
Protected 属性 | |
int32_t | m_num_neurons |
int32_t | m_width |
int32_t | m_height |
int32_t | m_num_parameters |
SGVector< int32_t > | m_input_indices |
SGVector< int32_t > | m_input_sizes |
int32_t | m_batch_size |
SGMatrix< float64_t > | m_activations |
SGMatrix< float64_t > | m_activation_gradients |
SGMatrix< float64_t > | m_local_gradients |
SGMatrix< bool > | m_dropout_mask |
default constructor
在文件 NeuralLinearLayer.cpp 第 44 行定义.
CNeuralLinearLayer | ( | int32_t | num_neurons | ) |
|
virtual |
在文件 NeuralLinearLayer.h 第 75 行定义.
|
inherited |
Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.
dict | dictionary of parameters to be built. |
在文件 SGObject.cpp 第 597 行定义.
|
virtualinherited |
Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.
在文件 SGObject.cpp 第 714 行定义.
|
virtual |
Computes the activations of the neurons in this layer, results should be stored in m_activations. To be used only with non-input layers
parameters | Vector of size get_num_parameters(), contains the parameters of the layer |
layers | Array of layers that form the network that this layer is being used with |
重载 CNeuralLayer .
被 CNeuralLeakyRectifiedLinearLayer, CNeuralLogisticLayer, CNeuralRectifiedLinearLayer , 以及 CNeuralSoftmaxLayer 重载.
在文件 NeuralLinearLayer.cpp 第 77 行定义.
Computes the activations of the neurons in this layer, results should be stored in m_activations. To be used only with input layers
inputs | activations of the neurons in the previous layer, matrix of size previous_layer_num_neurons * batch_size |
被 CNeuralInputLayer 重载.
在文件 NeuralLayer.h 第 153 行定义.
Computes
\[ \frac{\lambda}{N} \sum_{k=0}^{N-1} \left \| J(x_k) \right \|^2_F \]
where \( \left \| J(x_k)) \right \|^2_F \) is the Frobenius norm of the Jacobian of the activations of the hidden layer with respect to its inputs, \( N \) is the batch size, and \( \lambda \) is the contraction coefficient.
Should be implemented by layers that support being used as a hidden layer in a contractive autoencoder.
parameters | Vector of size get_num_parameters(), contains the parameters of the layer |
重载 CNeuralLayer .
被 CNeuralLogisticLayer , 以及 CNeuralRectifiedLinearLayer 重载.
在文件 NeuralLinearLayer.cpp 第 295 行定义.
|
virtual |
Adds the gradients of
\[ \frac{\lambda}{N} \sum_{k=0}^{N-1} \left \| J(x_k) \right \|^2_F \]
to the gradients vector, where \( \left \| J(x_k)) \right \|^2_F \) is the Frobenius norm of the Jacobian of the activations of the hidden layer with respect to its inputs, \( N \) is the batch size, and \( \lambda \) is the contraction coefficient.
Should be implemented by layers that support being used as a hidden layer in a contractive autoencoder.
parameters | Vector of size get_num_parameters(), contains the parameters of the layer |
gradients | Vector of size get_num_parameters(). Gradients of the contraction term will be added to it |
被 CNeuralLogisticLayer , 以及 CNeuralRectifiedLinearLayer 重载.
在文件 NeuralLinearLayer.cpp 第 304 行定义.
Computes the error between the layer's current activations and the given target activations. Should only be used with output layers
targets | desired values for the layer's activations, matrix of size num_neurons*batch_size |
重载 CNeuralLayer .
被 CNeuralSoftmaxLayer 重载.
在文件 NeuralLinearLayer.cpp 第 260 行定义.
|
virtual |
Computes the gradients that are relevent to this layer:
The gradients of the error with respect to the layer's parameters -The gradients of the error with respect to the layer's inputs
Input gradients for layer i that connects into this layer as input are added to m_layers.element(i).get_activation_gradients()
Deriving classes should make sure to account for dropout [Hinton, 2012] during gradient computations
parameters | Vector of size get_num_parameters(), contains the parameters of the layer |
targets | a matrix of size num_neurons*batch_size. If the layer is being used as an output layer, targets is the desired values for the layer's activations, otherwise it's an empty matrix |
layers | Array of layers that form the network that this layer is being used with |
parameter_gradients | Vector of size get_num_parameters(). To be filled with gradients of the error with respect to each parameter of the layer |
重载 CNeuralLayer .
在文件 NeuralLinearLayer.cpp 第 135 行定义.
Computes the gradients of the error with respect to this layer's pre-activations. Results are stored in m_local_gradients.
This is used by compute_gradients() and can be overriden to implement layers with different activation functions
targets | a matrix of size num_neurons*batch_size. If the layer is being used as an output layer, targets is the desired values for the layer's activations, otherwise it's an empty matrix |
被 CNeuralLogisticLayer, CNeuralRectifiedLinearLayer , 以及 CNeuralSoftmaxLayer 重载.
在文件 NeuralLinearLayer.cpp 第 242 行定义.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
在文件 SGObject.cpp 第 198 行定义.
|
virtualinherited |
Applies dropout [Hinton, 2012] to the activations of the layer
If is_training is true, fills m_dropout_mask with random values (according to dropout_prop) and multiplies it into the activations, otherwise, multiplies the activations by (1-dropout_prop) to compensate for using dropout during training
在文件 NeuralLayer.cpp 第 90 行定义.
Constrains the weights of each neuron in the layer to have an L2 norm of at most max_norm
parameters | pointer to the layer's parameters, array of size get_num_parameters() |
max_norm | maximum allowable norm for a neuron's weights |
重载 CNeuralLayer .
在文件 NeuralLinearLayer.cpp 第 271 行定义.
Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!
May be overwritten but please do with care! Should not be necessary in most cases.
other | object to compare with |
accuracy | accuracy to use for comparison (optional) |
tolerant | allows linient check on float equality (within accuracy) |
在文件 SGObject.cpp 第 618 行定义.
Gets the layer's activation gradients, a matrix of size num_neurons * batch_size
在文件 NeuralLayer.h 第 294 行定义.
Gets the layer's activations, a matrix of size num_neurons * batch_size
在文件 NeuralLayer.h 第 287 行定义.
|
inherited |
|
inherited |
|
inherited |
|
virtualinherited |
Returns the height assuming that the layer's activations are interpreted as images (i.e for convolutional nets)
在文件 NeuralLayer.h 第 265 行定义.
|
virtualinherited |
Gets the indices of the layers that are connected to this layer as input
在文件 NeuralLayer.h 第 313 行定义.
Gets the layer's local gradients, a matrix of size num_neurons * batch_size
在文件 NeuralLayer.h 第 304 行定义.
|
inherited |
在文件 SGObject.cpp 第 498 行定义.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
param_name | name of the parameter |
在文件 SGObject.cpp 第 522 行定义.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
在文件 SGObject.cpp 第 535 行定义.
|
virtual |
Returns the name of the SGSerializable instance. It MUST BE the CLASS NAME without the prefixed `C'.
重载 CNeuralLayer .
被 CNeuralLogisticLayer, CNeuralRectifiedLinearLayer, CNeuralSoftmaxLayer , 以及 CNeuralLeakyRectifiedLinearLayer 重载.
在文件 NeuralLinearLayer.h 第 213 行定义.
|
virtualinherited |
Gets the number of neurons in the layer
在文件 NeuralLayer.h 第 251 行定义.
|
virtualinherited |
Gets the number of parameters used in this layer
在文件 NeuralLayer.h 第 281 行定义.
|
virtualinherited |
Returns the width assuming that the layer's activations are interpreted as images (i.e for convolutional nets)
在文件 NeuralLayer.h 第 258 行定义.
|
virtual |
Initializes the layer, computes the number of parameters needed for the layer
layers | Array of layers that form the network that this layer is being used with |
input_indices | Indices of the layers that are connected to this layer as input |
重载 CNeuralLayer .
在文件 NeuralLinearLayer.cpp 第 53 行定义.
|
virtual |
Initializes the layer's parameters. The layer should fill the given arrays with the initial value for its parameters
parameters | Vector of size get_num_parameters() |
parameter_regularizable | Vector of size get_num_parameters(). This controls which of the layer's parameter are subject to regularization, i.e to turn off regularization for parameter i, set parameter_regularizable[i] = false. This is usally used to turn off regularization for bias parameters. |
sigma | standard deviation of the gaussian used to random the parameters |
重载 CNeuralLayer .
在文件 NeuralLinearLayer.cpp 第 63 行定义.
|
virtualinherited |
If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.
generic | set to the type of the generic if returning TRUE |
在文件 SGObject.cpp 第 296 行定义.
|
virtualinherited |
returns true if the layer is an input layer. Input layers are the root layers of a network, that is, they don't receive signals from other layers, they receive signals from the inputs features to the network.
Local and activation gradients are not computed for input layers
被 CNeuralInputLayer 重载.
在文件 NeuralLayer.h 第 127 行定义.
|
virtualinherited |
Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!
file | where to load from |
prefix | prefix for members |
在文件 SGObject.cpp 第 369 行定义.
|
protectedvirtualinherited |
Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.
ShogunException | will be thrown if an error occurs. |
被 CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel , 以及 CExponentialKernel 重载.
在文件 SGObject.cpp 第 426 行定义.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.
ShogunException | will be thrown if an error occurs. |
被 CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.
在文件 SGObject.cpp 第 421 行定义.
|
virtualinherited |
在文件 SGObject.cpp 第 262 行定义.
|
inherited |
prints all parameter registered for model selection and their type
在文件 SGObject.cpp 第 474 行定义.
|
virtualinherited |
|
virtualinherited |
Save this object to file.
file | where to save the object; will be closed during returning if PREFIX is an empty string. |
prefix | prefix for members |
在文件 SGObject.cpp 第 314 行定义.
|
protectedvirtualinherited |
Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.
ShogunException | will be thrown if an error occurs. |
被 CKernel 重载.
在文件 SGObject.cpp 第 436 行定义.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.
ShogunException | will be thrown if an error occurs. |
被 CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.
在文件 SGObject.cpp 第 431 行定义.
|
virtualinherited |
Sets the batch_size and allocates memory for m_activations and m_input_gradients accordingly. Must be called before forward or backward propagation is performed
batch_size | number of training/test cases the network is currently working with |
被 CNeuralConvolutionalLayer 重载.
在文件 NeuralLayer.cpp 第 75 行定义.
|
inherited |
在文件 SGObject.cpp 第 41 行定义.
|
inherited |
在文件 SGObject.cpp 第 46 行定义.
|
inherited |
在文件 SGObject.cpp 第 51 行定义.
|
inherited |
在文件 SGObject.cpp 第 56 行定义.
|
inherited |
在文件 SGObject.cpp 第 61 行定义.
|
inherited |
在文件 SGObject.cpp 第 66 行定义.
|
inherited |
在文件 SGObject.cpp 第 71 行定义.
|
inherited |
在文件 SGObject.cpp 第 76 行定义.
|
inherited |
在文件 SGObject.cpp 第 81 行定义.
|
inherited |
在文件 SGObject.cpp 第 86 行定义.
|
inherited |
在文件 SGObject.cpp 第 91 行定义.
|
inherited |
在文件 SGObject.cpp 第 96 行定义.
|
inherited |
在文件 SGObject.cpp 第 101 行定义.
|
inherited |
在文件 SGObject.cpp 第 106 行定义.
|
inherited |
在文件 SGObject.cpp 第 111 行定义.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
|
inherited |
|
virtualinherited |
Gets the number of neurons in the layer
num_neurons | number of neurons in the layer |
在文件 NeuralLayer.h 第 271 行定义.
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
被 CGaussianKernel 重载.
在文件 SGObject.cpp 第 192 行定义.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
在文件 SGObject.cpp 第 303 行定义.
|
virtualinherited |
Updates the hash of current parameter combination
在文件 SGObject.cpp 第 248 行定义.
|
inherited |
For autoencoders, specifies the position of the layer in the autoencoder, i.e an encoding layer or a decoding layer. Default value is NLAP_NONE
在文件 NeuralLayer.h 第 343 行定义.
|
inherited |
For hidden layers in a contractive autoencoders [Rifai, 2011] a term:
\[ \frac{\lambda}{N} \sum_{k=0}^{N-1} \left \| J(x_k) \right \|^2_F \]
is added to the error, where \( \left \| J(x_k)) \right \|^2_F \) is the Frobenius norm of the Jacobian of the activations of the hidden layer with respect to its inputs, \( N \) is the batch size, and \( \lambda \) is the contraction coefficient.
Default value is 0.0.
在文件 NeuralLayer.h 第 338 行定义.
|
inherited |
probabilty of dropping out a neuron in the layer
在文件 NeuralLayer.h 第 327 行定义.
|
inherited |
io
在文件 SGObject.h 第 369 行定义.
|
inherited |
Should be true if the layer is currently used during training initial value is false
在文件 NeuralLayer.h 第 324 行定义.
gradients of the error with respect to the layer's inputs size previous_layer_num_neurons * batch_size
在文件 NeuralLayer.h 第 381 行定义.
activations of the neurons in this layer size num_neurons * batch_size
在文件 NeuralLayer.h 第 376 行定义.
|
protectedinherited |
number of training/test cases the network is currently working with
在文件 NeuralLayer.h 第 371 行定义.
|
protectedinherited |
binary mask that determines whether a neuron will be kept or dropped out during the current iteration of training size num_neurons * batch_size
在文件 NeuralLayer.h 第 393 行定义.
|
inherited |
parameters wrt which we can compute gradients
在文件 SGObject.h 第 384 行定义.
|
inherited |
Hash of parameter values
在文件 SGObject.h 第 387 行定义.
|
protectedinherited |
Width of the image (if the layer's activations are to be interpreted as images. Default value is 1
在文件 NeuralLayer.h 第 357 行定义.
|
protectedinherited |
Indices of the layers that are connected to this layer as input
在文件 NeuralLayer.h 第 363 行定义.
|
protectedinherited |
Number of neurons in the layers that are connected to this layer as input
在文件 NeuralLayer.h 第 368 行定义.
gradients of the error with respect to the layer's pre-activations, this is usually used as a buffer when computing the input gradients size num_neurons * batch_size
在文件 NeuralLayer.h 第 387 行定义.
|
inherited |
model selection parameters
在文件 SGObject.h 第 381 行定义.
|
protectedinherited |
Number of neurons in this layer
在文件 NeuralLayer.h 第 347 行定义.
|
protectedinherited |
Number of neurons in this layer
在文件 NeuralLayer.h 第 360 行定义.
|
inherited |
parameters
在文件 SGObject.h 第 378 行定义.
|
protectedinherited |
Width of the image (if the layer's activations are to be interpreted as images. Default value is m_num_neurons
在文件 NeuralLayer.h 第 352 行定义.
|
inherited |
parallel
在文件 SGObject.h 第 372 行定义.
|
inherited |
version
在文件 SGObject.h 第 375 行定义.